Knowledge from Probability

• URL: http://arxiv.org/abs/2106.11501v1
• Date: Tue, 22 Jun 2021 02:46:22 GMT
• Title: Knowledge from Probability
• Authors: Jeremy Goodman, Bernhard Salow
• Abstract summary: We investigate predictions concerning knowledge about the future, about laws of nature, and about the values of inexactly measured quantities. The analysis combines a theory of knowledge and belief formulated in terms of relations of comparative normality with a probabilistic reduction of those relations. It predicts that only highly probable propositions are believed, and that many widely held principles of belief-revision fail.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We give a probabilistic analysis of inductive knowledge and belief and explore its predictions concerning knowledge about the future, about laws of nature, and about the values of inexactly measured quantities. The analysis combines a theory of knowledge and belief formulated in terms of relations of comparative normality with a probabilistic reduction of those relations. It predicts that only highly probable propositions are believed, and that many widely held principles of belief-revision fail.

Related papers

• Epistemic Boundaries and Quantum Uncertainty: What Local Observers Can (Not) Predict [0.0]
  We argue that post-quantum theories can offer a predictive advantage while conforming to the Born rule on average. We uncover a fascinating possibility: When the assumption of reliable intersubjectivity between different observers is violated, subjective predictive advantage can, in principle, exist. The findings reconcile us to quantum uncertainty as an aspect of limits on Nature's predictability.
  arXiv  Detail & Related papers  (2023-10-13T14:09:18Z)
• Crystal: Introspective Reasoners Reinforced with Self-Feedback [118.53428015478957]
  We propose a novel method to develop an introspective commonsense reasoner, Crystal. To tackle commonsense problems, it first introspects for knowledge statements related to the given question, and subsequently makes an informed prediction that is grounded in the previously introspected knowledge. Experiments show that Crystal significantly outperforms both the standard supervised finetuning and chain-of-thought distilled methods, and enhances the transparency of the commonsense reasoning process.
  arXiv  Detail & Related papers  (2023-10-07T21:23:58Z)
• Belief Revision from Probability [0.0]
  We develop a question-relative, probabilistic account of belief. We show that the principles it validates are much weaker than those of orthodox theories of belief revision like AGM. We conclude by arguing that the present framework compares favorably to the rival probabilistic accounts of belief developed by Leitgeb and by Lin and Kelly.
  arXiv  Detail & Related papers  (2023-07-11T07:11:30Z)
• Reconciling Predictive and Statistical Parity: A Causal Approach [68.59381759875734]
  We propose a new causal decomposition formula for the fairness measures associated with predictive parity. We show that the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions.
  arXiv  Detail & Related papers  (2023-06-08T09:23:22Z)
• Uncertain Evidence in Probabilistic Models and Stochastic Simulators [80.40110074847527]
  We consider the problem of performing Bayesian inference in probabilistic models where observations are accompanied by uncertainty, referred to as uncertain evidence' We explore how to interpret uncertain evidence, and by extension the importance of proper interpretation as it pertains to inference about latent variables. We devise concrete guidelines on how to account for uncertain evidence and we provide new insights, particularly regarding consistency.
  arXiv  Detail & Related papers  (2022-10-21T20:32:59Z)
• Uncertainty relations from graph theory [0.0]
  Quantum measurements are inherently probabilistic and quantum theory often forbids to precisely predict the outcomes of simultaneous measurements. We derive uncertainty relations valid for any set of dichotomic observables. As applications, our results can be straightforwardly used to formulate entropic uncertainty relations, separability criteria and entanglement witnesses.
  arXiv  Detail & Related papers  (2022-07-05T17:57:31Z)
• The Unreasonable Effectiveness of Deep Evidential Regression [72.30888739450343]
  A new approach with uncertainty-aware regression-based neural networks (NNs) shows promise over traditional deterministic methods and typical Bayesian NNs. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a quantification rather than an exact uncertainty.
  arXiv  Detail & Related papers  (2022-05-20T10:10:32Z)
• Degrees of riskiness, falsifiability, and truthlikeness. A neo-Popperian account applicable to probabilistic theories [0.0]
  We take a fresh look at three Popperian concepts: riskiness, falsifiability, and truthlikeness. We make explicit the dimensions that underlie the notion of riskiness. We examine if and how degrees of falsifiability can be defined, and how they are related to various dimensions of the concept of riskiness.
  arXiv  Detail & Related papers  (2021-07-08T11:36:50Z)
• DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
  Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner. We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
  arXiv  Detail & Related papers  (2021-02-16T23:50:35Z)
• Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
  We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-01-05T18:54:11Z)
• From Probability to Consilience: How Explanatory Values Implement Bayesian Reasoning [0.10152838128195464]
  We propose a Bayesian account of how explanatory values fit together to guide explanation. The resulting taxonomy provides a set of predictors for which explanations people prefer. This framework also enables us to reinterpret the explanatory vices that drive conspiracy theories, delusions, and extremist ideologies.
  arXiv  Detail & Related papers  (2020-06-03T16:11:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.